基于深度学习优化SSD算法的硅片隐裂检测识别
|
摘要
针对传统的通过机器视觉和机器学习算法检测识别硅片隐裂所存在的精度低、识别率差、检测耗时长的问题,提出一种新的检测方法,即采用优化的单个深度神经网络来检测图像中的目标的方法 (Single Shot MultiBox Detector,SSD),对SSD的特征提取网络融合了密集连接卷积网络(Densely Connected Convolutional Networks,Dense Net),解决了原网络对低于0. 1 mm的裂痕提取困难的缺点。通过实验,优化后的SSD检测算法对低于0. 01 mm裂纹检测精度比传统的通过纹理滤波和SVM分类检测算法提高了22%,比没有优化的SSD算法检测准确率提高了6%。证明了本文作者所提方法的有效性。
By machine vision and machine learning algorithms for traditional low existed in the recognition of the wafer cracked detection precision,the recognition rate is poor,and testing takes a long time of problem,a new detection method was proposed. The optimized neural network to detect targets in the images of the single depth method of single shot multi Box detector( SSD),feature extraction of SSD combined with dense connectivity convolution network( Dense Net),the defection difficulty of extracting crack of less than 0. 1 mm was solved in the original network. Through the experiment,the optimized SSD detection algorithm improved the detection accuracy of crack under 0. 01 mm by 22% as compared with the traditional texture filtering and state vector machine( SVM) classification detection algorithm. The detection accuracy is 6% higher than the non-optimized SSD algorithm. The validity of this method is proved.
By machine vision and machine learning algorithms for traditional low existed in the recognition of the wafer cracked detection precision,the recognition rate is poor,and testing takes a long time of problem,a new detection method was proposed. The optimized neural network to detect targets in the images of the single depth method of single shot multi Box detector( SSD),feature extraction of SSD combined with dense connectivity convolution network( Dense Net),the defection difficulty of extracting crack of less than 0. 1 mm was solved in the original network. Through the experiment,the optimized SSD detection algorithm improved the detection accuracy of crack under 0. 01 mm by 22% as compared with the traditional texture filtering and state vector machine( SVM) classification detection algorithm. The detection accuracy is 6% higher than the non-optimized SSD algorithm. The validity of this method is proved.
引文
[1]李春龙,潘丰.基于机器视觉的硅片检测分类系统设计[J].江南大学学报(自然科学版),2013,12(6):654-657.LI C L,PAN F.System Design of Silicon Detection Classification Based on Machine Vision[J].Journal of Jiangnan U-niversity(Natural Science Edition),2013,12(6):654-657.
[2]吴浩.基于机器视觉的铜条表面缺陷检测系统的研究[J].仪表技术与传感器,2016(7):87-92.WU H.Research of Copper Bar Surface Defects Inspection System Based on Machine Vision[J].Instrument Technique and Sensor,2016(7):87-92.
[3]崔光茫,赵巨峰,辛青.基于工业生产设备表面缺陷检测的实验设计[J].实验室研究与探索,2017,36(4):165-244.CUI G M,ZHAO J F,XIN Q.Experiment Design for Surface Defect Inspection Base on Industry Production Equipment[J].Research and Exploration in Laboratory,2017,36(4):165-244.
[4]BIANCO M L,FERRER-GALLEGO P,GRILLO O,et al.Seed Image Analysis Provides Evidence of Taxonomic Differentiation within the Medicago L.sect.Dendrotelis(Fabaceae)[J].Systematics and Biodiversity,2015,13(5):484-495.
[5]KRIZHEVSKY A,SUTSKEVER I,HINTON G E.Imagenet Classi-fication with Deep Convolutional Neural Networks[C]//Proceedings of Advances in Neural Information Processing Systems,2012:1097-1105.
[6]乔丽,赵尔敦,刘俊杰,等.基于CNN的工件缺陷检测方法研究[J].计算机科学,2017,44(11):239-243.
[7]OUYANG W L,ZENG X Y.DeepID-Net:Object Detection with Deformable Part Based Convolutional Neural Networks[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2017,39(7):1320-1334.
[8]高常,宏杰,孙聚运,等.机器视觉在板材表面缺陷检测中的应用[J].机械设计与制造,2017(8):144-146.GAO C,HONG J,SUN J Y,et al.Application of Machine Vision in Detection of Wood Surface Defects[J].Machinery Design&Manufacture,2017(8):144-146.
[9]GIRSHICK R,DONAHUE J,DARRELL T,et al.Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition,2014:580-587.
[10]GIRSHICK R.Fast R-CNN[C]//Proceedings of the IEEE International Conference on Computer Vision,2015:1440-1448.
[11]REN S,HE K,GIRSHICK R,et al.Faster R-CNN:Towards Real-time Object Detection with Region Proposal Net-works[C]//Proceedings of Advances in Neural Information Processing Systems,2015:91-99.
[12]REDMON J,DIVVALA S,GIRSHICK R,et al.You Only Look Once:Unified,Real-time Object Detection[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition:IEEE,2016:779-788.
[13]LIU W,ANGUELOV D,ERHAN D,et al.SSD:Single Shot MultiBox Detector[C]//Proceedings of European Conference on Computer Vision,2016:1512-1520.
[14]WANG Y Y,WANG C,ZHANG H.Combining a Single Shot Multibox Detector with Transfer Learning for Ship Detection Using Sentinel-1 SAR Images[J].Remote Sensing Letters,2018,9(8):780-788.
[15]AYAR B,STAMM M C.Constrained Convolutional Neural Networks:A New Approach Towards General Purpose Image Manipulation Detection[J].IEEE Transactions on Information Forensics and Security,2018:11(13):2691-2706.
[16]HUANG G,LIU Z,LAURENS V D M.Densely Connected Convolutional Networks[C]//Proceedings of the IEEEConference on Computer Vision and Pattern Recognition,2017:608-613.
[17]HE K,ZHANG X,REN S,et al.Deep Residual Learning for Image Recognition[C]//Proceedings of the IEEEConference on Computer Vision and Pattern Recognition,2016:770-778.
[18]WU Z,SHEN C,HENGEL A.Wider or Deeper:Revisiting the Resnet Model for Visual Recognition[J].Ar Xiv Preprint Ar Xiv:1611.10080,2016.
[19]ZHOU F Q,LI X J,LI Z X.High-frequency Details Enhancing Dense Net for Super-resolution[J].Neurocomputing,2018,290:34-42.
[20]TAO Y,XU M Z,LU Z Y,et al.DenseNet-Based DepthWidth Double Reinforced Deep Learning Neural Network for High-Resolution Remote Sensing Image Per-Pixel Classification[J].Remote Sensing Image Processing,2018,10(5):14-21.
[2]吴浩.基于机器视觉的铜条表面缺陷检测系统的研究[J].仪表技术与传感器,2016(7):87-92.WU H.Research of Copper Bar Surface Defects Inspection System Based on Machine Vision[J].Instrument Technique and Sensor,2016(7):87-92.
[3]崔光茫,赵巨峰,辛青.基于工业生产设备表面缺陷检测的实验设计[J].实验室研究与探索,2017,36(4):165-244.CUI G M,ZHAO J F,XIN Q.Experiment Design for Surface Defect Inspection Base on Industry Production Equipment[J].Research and Exploration in Laboratory,2017,36(4):165-244.
[4]BIANCO M L,FERRER-GALLEGO P,GRILLO O,et al.Seed Image Analysis Provides Evidence of Taxonomic Differentiation within the Medicago L.sect.Dendrotelis(Fabaceae)[J].Systematics and Biodiversity,2015,13(5):484-495.
[5]KRIZHEVSKY A,SUTSKEVER I,HINTON G E.Imagenet Classi-fication with Deep Convolutional Neural Networks[C]//Proceedings of Advances in Neural Information Processing Systems,2012:1097-1105.
[6]乔丽,赵尔敦,刘俊杰,等.基于CNN的工件缺陷检测方法研究[J].计算机科学,2017,44(11):239-243.
[7]OUYANG W L,ZENG X Y.DeepID-Net:Object Detection with Deformable Part Based Convolutional Neural Networks[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2017,39(7):1320-1334.
[8]高常,宏杰,孙聚运,等.机器视觉在板材表面缺陷检测中的应用[J].机械设计与制造,2017(8):144-146.GAO C,HONG J,SUN J Y,et al.Application of Machine Vision in Detection of Wood Surface Defects[J].Machinery Design&Manufacture,2017(8):144-146.
[9]GIRSHICK R,DONAHUE J,DARRELL T,et al.Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition,2014:580-587.
[10]GIRSHICK R.Fast R-CNN[C]//Proceedings of the IEEE International Conference on Computer Vision,2015:1440-1448.
[11]REN S,HE K,GIRSHICK R,et al.Faster R-CNN:Towards Real-time Object Detection with Region Proposal Net-works[C]//Proceedings of Advances in Neural Information Processing Systems,2015:91-99.
[12]REDMON J,DIVVALA S,GIRSHICK R,et al.You Only Look Once:Unified,Real-time Object Detection[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition:IEEE,2016:779-788.
[13]LIU W,ANGUELOV D,ERHAN D,et al.SSD:Single Shot MultiBox Detector[C]//Proceedings of European Conference on Computer Vision,2016:1512-1520.
[14]WANG Y Y,WANG C,ZHANG H.Combining a Single Shot Multibox Detector with Transfer Learning for Ship Detection Using Sentinel-1 SAR Images[J].Remote Sensing Letters,2018,9(8):780-788.
[15]AYAR B,STAMM M C.Constrained Convolutional Neural Networks:A New Approach Towards General Purpose Image Manipulation Detection[J].IEEE Transactions on Information Forensics and Security,2018:11(13):2691-2706.
[16]HUANG G,LIU Z,LAURENS V D M.Densely Connected Convolutional Networks[C]//Proceedings of the IEEEConference on Computer Vision and Pattern Recognition,2017:608-613.
[17]HE K,ZHANG X,REN S,et al.Deep Residual Learning for Image Recognition[C]//Proceedings of the IEEEConference on Computer Vision and Pattern Recognition,2016:770-778.
[18]WU Z,SHEN C,HENGEL A.Wider or Deeper:Revisiting the Resnet Model for Visual Recognition[J].Ar Xiv Preprint Ar Xiv:1611.10080,2016.
[19]ZHOU F Q,LI X J,LI Z X.High-frequency Details Enhancing Dense Net for Super-resolution[J].Neurocomputing,2018,290:34-42.
[20]TAO Y,XU M Z,LU Z Y,et al.DenseNet-Based DepthWidth Double Reinforced Deep Learning Neural Network for High-Resolution Remote Sensing Image Per-Pixel Classification[J].Remote Sensing Image Processing,2018,10(5):14-21.